Multiscale fusion CNN-based super-resolution magnetic resonance image reconstruction method

Abstract

The invention relates to a multiscale fusion CNN-based super-resolution magnetic resonance image reconstruction method. The method comprises the following steps of: firstly preprocessing a low-resolution image and a corresponding high-resolution image, and constructing a training data set and a label data set; constructing a multiscale information-fusion full-convolutional neural network; inputting the training data set into the constructed multiscale information-fusion full-convolutional neural network to carry out training so as to obtain a learnt convolutional neural network model; inputting the test low-resolution image into the learnt convolutional neural network to obtain a reconstructed high-resolution image. Through a multiscale fusion unit, features of different convolutional layers are mapped and fused, so that flat structures stacked by multiple convolutional layers of traditional convolutional neural networks are overcome, the convergence speeds of the networks can be improved, lost image details of low-resolution images can be reconstructed more rapidly, the reconstruction time can be shortened, the reconstruction efficiency can be improved and the resource waste can be avoided.

Description

technical field [0001] The invention belongs to the field of image processing, in particular to a method for super-resolution reconstruction of magnetic resonance images based on multi-scale fusion CNN. Background technique [0002] Structural magnetic resonance images with higher spatial resolution have fewer artifacts, which directly affect the accuracy of subsequent image processing and medical diagnosis, such as registration and segmentation. However, due to limitations in physical equipment, acquisition technology, and economy, the spatial resolution of existing magnetic resonance images is affected to a certain extent. [0003] In the field of image processing, traditional super-resolution reconstruction methods mainly use interpolation methods, such as bilinear interpolation, B-spline interpolation and other methods. These methods assume the smooth nature of local regions and estimate newly interpolated voxel values ​​from neighboring voxels. However, the interpolat...

AI Technical Summary

Problems solved by technology

In the medical field, it is difficult to obtain a large amount of magnetic resonance image data, so it is difficult to guarantee the convergence and reconstruction accuracy of the network directly using the traditional convolutional neural network

Images